{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:00:02Z","timestamp":1760144402105,"version":"build-2065373602"},"reference-count":48,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T00:00:00Z","timestamp":1713571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003246","name":"Dutch Research Council","doi-asserted-by":"publisher","award":["OCENW.KLEIN.387","001 (Processo 300904\/2023-1)"],"award-info":[{"award-number":["OCENW.KLEIN.387","001 (Processo 300904\/2023-1)"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior\u2014Brasil (CAPES)","award":["OCENW.KLEIN.387","001 (Processo 300904\/2023-1)"],"award-info":[{"award-number":["OCENW.KLEIN.387","001 (Processo 300904\/2023-1)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Particles"],"abstract":"<jats:p>Isotopic composition measurements of singly charged cosmic rays (CR) provide essential insights into CR transport in the Galaxy. The Alpha Magnetic Spectrometer (AMS-02) can identify singly charged isotopes up to about 10 GeV\/n. However, their identification presents challenges due to the small abundance of CR deuterons compared to the proton background. In particular, a high accuracy for the velocity measured by a ring-imaging Cherenkov detector (RICH) is needed to achieve a good isotopic mass separation over a wide range of energies. The velocity measurement with the RICH is particularly challenging for Z=1 isotopes due to the low number of photons produced in the Cherenkov rings. This faint signal is easily disrupted by noisy hits leading to a misreconstruction of the particles\u2019 ring. Hence, an efficient background reduction process is needed to ensure the quality of the reconstructed Cherenkov rings and provide a correct measurement of the particles\u2019 velocity. Machine learning methods, particularly boosted decision trees, are well suited for this task, but their performance relies on the choice of the features needed for their training phase. While physics-driven feature selection methods based on the knowledge of the detector are often used, machine learning algorithms for automated feature selection can provide a helpful alternative that optimises the classification method\u2019s performance. We compare five algorithms for selecting the feature samples for RICH background reduction, achieving the best results with the Random Forest method. We also test its performance against the physics-driven selection method, obtaining better results.<\/jats:p>","DOI":"10.3390\/particles7020024","type":"journal-article","created":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T12:38:41Z","timestamp":1713789521000},"page":"417-434","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Feature Selection Techniques for CR Isotope Identification with the AMS-02 Experiment in Space"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3805-2983","authenticated-orcid":false,"given":"Marta","family":"Borchiellini","sequence":"first","affiliation":[{"name":"Kapteyn Astronomical Institute, University of Groningen Landleven 12, 9747 AD Groningen, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2215-0133","authenticated-orcid":false,"given":"Leandro","family":"Mano","sequence":"additional","affiliation":[{"name":"National Council of Scientific and Technological Development, SHIS Q1, Edif\u00edcio Santos Dumont 203, Bras\u00edlia 71605-001, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8346-9941","authenticated-orcid":false,"given":"Fernando","family":"Bar\u00e3o","sequence":"additional","affiliation":[{"name":"Laborat\u00f3rio de Instrumenta\u00e7\u00e3o e F\u00edsica Experimental de Part\u00edculas (LIP), 1649-003 Lisboa, Portugal"},{"name":"Departamento de F\u00edsica, Instituto Superior T\u00e9cnico\u2014IST, Universidade de Lisboa\u2014UL, Avenida Rovisco Pais 1, 1049-001 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5338-6029","authenticated-orcid":false,"given":"Manuela","family":"Vecchi","sequence":"additional","affiliation":[{"name":"Kapteyn Astronomical Institute, University of Groningen Landleven 12, 9747 AD Groningen, The Netherlands"}]}],"member":"1968","published-online":{"date-parts":[[2024,4,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Gaisser, T.K., Engel, R., and Resconi, E. (2016). Cosmic Rays and Particle Physics, Cambridge University Press. [2nd ed.].","DOI":"10.1017\/CBO9781139192194"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"A88","DOI":"10.1051\/0004-6361\/201117927","article-title":"Constraining Galactic cosmic-ray parameters with Z \u2264 2 nuclei","volume":"539","author":"Coste","year":"2012","journal-title":"Astron. Astrophys."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1103\/RevModPhys.83.195","article-title":"Solar fusion cross sections. II. The pp chain and CNO cycles","volume":"83","author":"Adelberger","year":"2011","journal-title":"Rev. Mod. Phys."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"68","DOI":"10.3847\/0004-637X\/818\/1\/68","article-title":"Measurements of Cosmic-Ray Hydrogen and Helium Isotopes with the PAMELA experiment","volume":"818","author":"Adriani","year":"2016","journal-title":"Astrophys. J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1063\/1.1324352","article-title":"A measurement of cosmic ray deuterium from 0.5\u20132.9 GeV\/nucleon","volume":"528","author":"Barbier","year":"2000","journal-title":"AIP Conf. Proc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1086\/424027","article-title":"High-energy deuteron measurement with the CAPRICE98 experiment","volume":"615","author":"Papini","year":"2004","journal-title":"Astrophys. J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.physrep.2020.09.003","article-title":"The Alpha Magnetic Spectrometer (AMS) on the international space station: Part II\u2014Results from the first seven years","volume":"894","author":"Aguilar","year":"2021","journal-title":"Phys. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Delgado, C. (August, January 26). Precision Measurement of Cosmic Ray Deuterons with Alpha Magnetic Spectrometer. Proceedings of the 38th International Cosmic Ray Conference\u2014PoS(ICRC2023), Nagoya, Japan.","DOI":"10.22323\/1.444.0079"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1016\/j.nima.2005.09.022","article-title":"Studies of boosted decision trees for MiniBooNE particle identification","volume":"555","author":"Yang","year":"2005","journal-title":"Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrometers Detect. Assoc. Equip."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"P02018","DOI":"10.1088\/1748-0221\/17\/02\/P02018","article-title":"A Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programme","volume":"17","author":"Graziani","year":"2022","journal-title":"J. Instrum."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"221102","DOI":"10.1103\/PhysRevLett.113.221102","article-title":"Precision Measurement of the (e++e\u2212) Flux in Primary Cosmic Rays from 0.5 GeV to 1 TeV with the Alpha Magnetic Spectrometer on the International Space Station","volume":"113","author":"Aguilar","year":"2014","journal-title":"Phys. Rev. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"121101","DOI":"10.1103\/PhysRevLett.113.121101","article-title":"High Statistics Measurement of the Positron Fraction in Primary Cosmic Rays of 0.5\u2013500 GeV with the Alpha Magnetic Spectrometer on the International Space Station","volume":"113","author":"Accardo","year":"2014","journal-title":"Phys. Rev. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"141102","DOI":"10.1103\/PhysRevLett.110.141102","article-title":"First Result from the Alpha Magnetic Spectrometer on the International Space Station: Precision Measurement of the Positron Fraction in Primary Cosmic Rays of 0.5\u2013350 GeV","volume":"110","author":"Aguilar","year":"2013","journal-title":"Phys. Rev. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Graziani, M. (2016, January 10\u201314). Electron\/proton separation and analysis techniques used in the AMS-02 (e++e\u2212) flux measurement. Proceedings of the 37th International Conference on High Energy Physics (ICHEP), San Francisco, CA, USA.","DOI":"10.1016\/j.nuclphysbps.2015.09.388"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"168644","DOI":"10.1016\/j.nima.2023.168644","article-title":"Machine learning approach to the background reduction in singly charged cosmic-ray isotope measurements with AMS-02","volume":"1056","author":"Bueno","year":"2023","journal-title":"Nucl. Instrum. Meth. A"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"116182","DOI":"10.1016\/j.nuclphysb.2023.116182","article-title":"Automated feature selection procedure for particle jet classification","volume":"990","author":"Cristoforetti","year":"2023","journal-title":"Nucl. Phys. B"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4061","DOI":"10.1093\/mnras\/stab2389","article-title":"Classification of Fermi-LAT sources with deep learning using energy and time spectra","volume":"507","author":"Finke","year":"2021","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"03014","DOI":"10.1051\/epjconf\/202125103014","article-title":"The use of Boosted Decision Trees for Energy Reconstruction in JUNO experiment","volume":"251","author":"Gavrikov","year":"2021","journal-title":"EPJ Web Conf."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5377","DOI":"10.1093\/mnras\/staa166","article-title":"An investigation on the factors affecting machine learning classifications in gamma-ray astronomy","volume":"492","author":"Luo","year":"2020","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Herrera, L.J., Peixoto, C.J.T., Ba\u00f1os, O., Carceller, J.M., Carrillo, F., and Guill\u00e9n, A. (2020). Composition Classification of Ultra-High Energy Cosmic Rays. Entropy, 22.","DOI":"10.3390\/e22090998"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"161797","DOI":"10.1016\/j.nima.2019.01.024","article-title":"The AMS-02 RICH detector: Status and physics results","volume":"952","author":"Giovacchini","year":"2020","journal-title":"Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrometers Detect. Assoc. Equip."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"166564","DOI":"10.1016\/j.nima.2022.166564","article-title":"A parametric approach for the identification of single-charged isotopes with AMS-02","volume":"1031","author":"Bueno","year":"2022","journal-title":"Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrometers Detect. Assoc. Equip."},{"key":"ref_23","unstructured":"Jackson, J.D. (1998). Classical Electrodynamics, Wiley."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.nuclphysbps.2007.07.025","article-title":"The Ring Imaging Cherenkov detector of the AMS experiment: Test beam results with a prototype","volume":"172","author":"Arruda","year":"2007","journal-title":"Nucl. Phys. B Proc. Suppl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.nima.2009.12.027","article-title":"In-beam aerogel light yield characterization for the AMS RICH detector","volume":"614","author":"Arruda","year":"2010","journal-title":"Nucl. Instrum. Meth. A"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"163657","DOI":"10.1016\/j.nima.2020.163657","article-title":"Space application: The AMS RICH","volume":"970","author":"Giovacchini","year":"2020","journal-title":"Nucl. Instrum. Meth. A"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.nima.2010.09.036","article-title":"The AMS-02 RICH detector: Performance during ground-based data taking at CERN","volume":"639","author":"Pereira","year":"2011","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"ref_28","unstructured":"Barao, F., Aguilar-Benitez, M., Arruda, L., Baret, B., Barrau, A., Barreira, G., Belmont, E., Berdugo, J., Borges, J., and Buenerd, M. (2007, January 3\u20137). The AMS-RICH velocity and charge reconstruction. Proceedings of the 30th International Cosmic Ray Conference, Yucatan, Mexico."},{"key":"ref_29","unstructured":"Delgado Mendez, C.J. (2003). Medida de la velocidad de muones y nucleos ligeros con un prototipo del contador RICH del experimento AMS. [Ph.D. Thesis, Universidad Autonoma de Madrid]."},{"key":"ref_30","unstructured":"Eadie, W.T., Drijard, D., and James, F.E. (1971). Statistical Methods in Experimental Physics, World Scientific Publishing Company."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"106839","DOI":"10.1016\/j.csda.2019.106839","article-title":"Benchmark for filter methods for feature selection in high-dimensional classification data","volume":"143","author":"Bommert","year":"2020","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Dvornik, N., Schmid, C., and Mairal, J. (2020, January 23\u201328). Selecting relevant features from a multi-domain representation for few-shot classification. Proceedings of the Computer Vision\u2014ECCV 2020: 16th European Conference, Part X 16, Glasgow, UK.","DOI":"10.1007\/978-3-030-58607-2_45"},{"key":"ref_33","first-page":"1","article-title":"A hybrid generalization network for intelligent fault diagnosis of rotating machinery under unseen working conditions","volume":"70","author":"Han","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2663","DOI":"10.1007\/s40747-021-00637-x","article-title":"Feature dimensionality reduction: A review","volume":"8","author":"Jia","year":"2022","journal-title":"Complex Intell. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"101948","DOI":"10.1016\/j.inffus.2023.101948","article-title":"A survey on multi-label feature selection from perspectives of label fusion","volume":"100","author":"Qian","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e12553","DOI":"10.1111\/exsy.12553","article-title":"Ensemble feature selection in medical datasets: Combining filter, wrapper, and embedded feature selection results","volume":"37","author":"Chen","year":"2020","journal-title":"Expert Syst."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"101224","DOI":"10.1016\/j.ecoinf.2021.101224","article-title":"An evaluation of feature selection methods for environmental data","volume":"61","author":"Effrosynidis","year":"2021","journal-title":"Ecol. Inform."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Liu, C.H., Tsai, C.F., Sue, K.L., and Huang, M.W. (2020). The feature selection effect on missing value imputation of medical datasets. Appl. Sci., 10.","DOI":"10.3390\/app10072344"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"110145","DOI":"10.1016\/j.ymssp.2023.110145","article-title":"An automated vibration-based structural damage localization strategy using filter-type feature selection","volume":"190","author":"Alves","year":"2023","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2225","DOI":"10.1016\/j.patrec.2010.03.014","article-title":"Variable selection using random forests","volume":"31","author":"Genuer","year":"2010","journal-title":"Pattern Recognit. Lett."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Polat, H., Polat, O., and Cetin, A. (2020). Detecting DDoS attacks in software-defined networks through feature selection methods and machine learning models. Sustainability, 12.","DOI":"10.3390\/su12031035"},{"key":"ref_42","first-page":"176","article-title":"An overview of correlational research","volume":"91","author":"Seeram","year":"2019","journal-title":"Radiol. Technol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1007\/s11063-019-10185-8","article-title":"Daily activity feature selection in smart homes based on pearson correlation coefficient","volume":"51","author":"Liu","year":"2020","journal-title":"Neural Process. Lett."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/ijdkp.2015.5201","article-title":"A review on evaluation metrics for data classification evaluations","volume":"5","author":"Hossin","year":"2015","journal-title":"Int. J. Data Min. Knowl. Manag. Process"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Yacouby, R., and Axman, D. (2020, January 20). Probabilistic extension of precision, recall, and f1 score for more thorough evaluation of classification models. Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems, Online.","DOI":"10.18653\/v1\/2020.eval4nlp-1.9"},{"key":"ref_46","first-page":"1","article-title":"Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning","volume":"18","author":"Nogueira","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Mano, L.Y. (2018, January 3\u20135). Emotional condition in the Health Smart Homes environment: Emotion recognition using ensemble of classifiers. Proceedings of the 2018 Innovations in Intelligent Systems and Applications (INISTA), Thessaloniki, Greece.","DOI":"10.1109\/INISTA.2018.8466318"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"8467","DOI":"10.1007\/s00500-019-04411-7","article-title":"An intelligent and generic approach for detecting human emotions: A case study with facial expressions","volume":"24","author":"Mano","year":"2020","journal-title":"Soft Comput."}],"container-title":["Particles"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2571-712X\/7\/2\/24\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:31:35Z","timestamp":1760106695000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2571-712X\/7\/2\/24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,20]]},"references-count":48,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["particles7020024"],"URL":"https:\/\/doi.org\/10.3390\/particles7020024","relation":{},"ISSN":["2571-712X"],"issn-type":[{"type":"electronic","value":"2571-712X"}],"subject":[],"published":{"date-parts":[[2024,4,20]]}}}